INDEX

Explanations

terms related to prohibition or restriction

oai_token-act-pair · gpt-3.5-turbo

terms related to prohibition or restrictions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sonian

-0.95

=-=-=-=-

-0.87

Assembly

-0.84

izational

-0.78

Seattle

-0.76

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.72

OA

-0.71

IU

-0.71

minster

-0.71

okane

-0.70

POSITIVE LOGITS

 forb

1.07

bidden

0.92

 forbid

0.88

 forbidden

0.81

 forbids

0.78

 confir

0.76

 dared

0.72

tering

0.72

ptin

0.71

fully

0.70

Activations Density 0.010%

terms related to prohibition or restriction

terms related to prohibition or restrictions

No Comments

No Known Activations